Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/keyargo/custodian-kernel/huggingface-infernpx skills add KeyArgo/custodian-kernel --skill huggingface-infergit clone --depth 1 https://github.com/KeyArgo/custodian-kernelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/keyargo/custodian-kernel/huggingface-infer)<a href="https://agentmods.dev/skills/keyargo/custodian-kernel/huggingface-infer"><img src="https://agentmods.dev/badge/skills/keyargo/custodian-kernel/huggingface-infer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00340 |
| Opus 5 | $0.00010 | $0.00170 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
huggingface-infer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
89% identical to discord-webhook — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Huggingface Infer
Run inference on a HuggingFace model via the Inference API
Authority band
This tool runs under L1 authority in the Custodian kernel. Trivial autonomous spend or free side-effect — no human approval required.
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
| (see execute.py for full schema) |
Configuration
Set the required environment variables before use. Until configured, custodian tools run huggingface-infer returns a stub response indicating which variables are needed.
Usage
custodian tools run huggingface-infer --param value
Custodian governance
Every call to this tool passes through the Custodian kernel authority check before executing. The kernel verifies the current authority band, checks spending caps where applicable, logs the action to the OCSF audit trail, and escalates to a human operator if the action exceeds the declared band.
Adding this tool to any Hermes agent session requires no code changes —
declare custodian-band: L1 in the SKILL.md frontmatter and the kernel
wraps it automatically.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 51 lines · 19 tokens per session scan A 96fdd84f4d4c
huggingface-infer is a skill published in the GitHub repository KeyArgo/custodian-kernel (118 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to discord-webhook, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
hugging-face-dataset-creator
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.